boldsoftware/meat
meat.dev observed · 2026-10-09
Health v2 · maintenance only
53/100
- Activity 87
- Release rhythm 35
- Longevity 7
Flags: no_releases young no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 111
- days_rel: n/a
- days_push: 78
- n_releases_24m: 0
Adoption not part of the score
2081 stars · 76 forks observed · 2026-10-09
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
meat is a Go CLI tool that uses an LLM to abridge a code diff into a 'reading diff', reducing agent-written changes to the conceptually important parts for human review. It accepts git-style parameters to select commits and handles very large diffs by splitting them at file and hunk boundaries.
Use cases
- review agent-written code changes at the concept level
- summarize a large git commit into its important parts
- pre-process commits into readable diffs for faster review
- focus code review on architecture and algorithm choices instead of style
When to choose
- you need to review large AI-generated diffs quickly
- you want concept-level review rather than line-by-line nitpicking
- you want a simple Go CLI that integrates with git workflows
When to avoid
- you need exact line-by-line diff fidelity for compliance or security audits
- you don't want to send proprietary code to an LLM
- you need real-time review with no processing latency
Facets
cli-tool · maturity active
llm-inference code-review developer-tools cli developer-tools version-control large-language-models cli go cross-platform code-review diff-summarization ai-assisted-review git
1 source
- readme: https://github.com/boldsoftware/meat · fetched 2026-10-09 · e76d90430c54
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| boldsoftware/meat | main | 53 |
For agents
markdown · JSON · MCP: product_card(name="boldsoftware/meat")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem